INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.08

2:0.09

3:0.08

4:0.08

5:0.09

6:0.09

7:0.06

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

 tongue

-1.71

 mistaken

-1.63

 questioning

-1.58

 resent

-1.57

 reconc

-1.56

 tongues

-1.52

 derogatory

-1.52

 remark

-1.51

theless

-1.51

 deterior

-1.50

POSITIVE LOGITS

xa

1.84

ADA

1.80

EF

1.67

adata

1.60

ット

1.60

1.58

ATA

1.58

RR

1.57

RA

1.53

 Agenda

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.